Key points are not available for this paper at this time.
The Q-learning based geographic routing approaches suffer from problems of low converging speed and inefficient resources utilization in VANET due to the dynamic scale of Q-value table. In addition, the next hop selection based on local information can not always be conducive to the global message forwarding. In this letter, we propose an adaptive unmanned aerial vehicle (UAV) assisted geographic routing with Q-Learning. The routing scheme is divided into two components. In the aerial component, the global routing path is calculated by the fuzzy-logic and depth-first-search (DFS) algorithm using the UAV-collected information like the global road traffic, which is then forwarded to the ground requesting vehicle. In the ground component, the vehicle maintains a fix-sized Q-table converged with a well-designed reward function and forwards the routing request to the optimal node by looking up the Q-table filtered according to the global routing path. The simulation results show the proposed approach performs remarkably well in packet delivering and end-to-end delay.
Jiang et al. (2020) studied this question.